Search Results for author: Jun Lu

Found 39 papers, 3 papers with code

Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT

no code implementations WMT (EMNLP) 2020 Jiayi Wang, Ke Wang, Kai Fan, Yuqi Zhang, Jun Lu, Xin Ge, Yangbin Shi, Yu Zhao

We also apply an imitation learning strategy to augment a reasonable amount of pseudo APE training data, potentially preventing the model to overfit on the limited real training data and boosting the performance on held-out data.

Automatic Post-Editing Benchmarking +5

Alibaba Submission to the WMT20 Parallel Corpus Filtering Task

no code implementations WMT (EMNLP) 2020 Jun Lu, Xin Ge, Yangbin Shi, Yuqi Zhang

In the filtering task, three main methods are applied to evaluate the quality of the parallel corpus, i. e. a) Dual Bilingual GPT-2 model, b) Dual Conditional Cross-Entropy Model and c) IBM word alignment model.

Language Identification Machine Translation +4

Domain Separation Graph Neural Networks for Saliency Object Ranking

no code implementations CVPR 2024 Zijian Wu, Jun Lu, Jing Han, Lianfa Bai, Yi Zhang, Zhuang Zhao, Siyang Song

Then we propose a Shape-Texture Graph Domain Separation (STGDS) module to separate the task-relevant and irrelevant information of target objects by explicitly modelling the relationship between each pair of objects in terms of their shapes and textures respectively.

Graph Neural Network

DMSA: Dynamic Multi-scale Unsupervised Semantic Segmentation Based on Adaptive Affinity

1 code implementation1 Mar 2023 Kun Yang, Jun Lu

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions.

Unsupervised Semantic Segmentation

Bayesian Matrix Decomposition and Applications

no code implementations18 Feb 2023 Jun Lu

The sole aim of this book is to give a self-contained introduction to concepts and mathematical tools in Bayesian matrix decomposition in order to seamlessly introduce matrix decomposition techniques and their applications in subsequent sections.

Variational Inference

Feature Selection via the Intervened Interpolative Decomposition and its Application in Diversifying Quantitative Strategies

no code implementations29 Sep 2022 Jun Lu, Joerg Osterrieder

In this paper, we propose a probabilistic model for computing an interpolative decomposition (ID) in which each column of the observed matrix has its own priority or importance, so that the end result of the decomposition finds a set of features that are representative of the entire set of features, and the selected features also have higher priority than others.

Bayesian Inference feature selection

Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model

no code implementations26 Aug 2022 Lingsheng Kong, Bo Hu, Xiongchang Liu, Jun Lu, Jane You, Xiaofeng Liu

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain.

Image Classification Pseudo Label +2

Robust Bayesian Nonnegative Matrix Factorization with Implicit Regularizers

no code implementations22 Aug 2022 Jun Lu, Christine P. Chai

We introduce a probabilistic model with implicit norm regularization for learning nonnegative matrix factorization (NMF) that is commonly used for predicting missing values and finding hidden patterns in the data, in which the matrix factors are latent variables associated with each data dimension.

Bayesian Inference

Subtype-Aware Dynamic Unsupervised Domain Adaptation

no code implementations16 Aug 2022 Xiaofeng Liu, Fangxu Xing, Jia You, Jun Lu, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

In TPN, while the closeness of class centers between source and target domains is explicitly enforced in a latent space, the underlying fine-grained subtype structure and the cross-domain within-class compactness have not been fully investigated.

Unsupervised Domain Adaptation

A Hybrid Approach on Conditional GAN for Portfolio Analysis

no code implementations13 Jul 2022 Jun Lu, Danny Ding

The limitation of the CGAN or ACGAN framework stands in putting too much emphasis on generating series and finding the internal trends of the series rather than predicting the future trends.

Generative Adversarial Network Time Series +1

A note on VIX for postprocessing quantitative strategies

no code implementations8 Jul 2022 Jun Lu, Minhui Wu

In this note, we introduce how to use Volatility Index (VIX) for postprocessing quantitative strategies so as to increase the Sharpe ratio and reduce trading risks.

Comparative Study of Inference Methods for Interpolative Decomposition

no code implementations29 Jun 2022 Jun Lu

In this paper, we propose a probabilistic model with automatic relevance determination (ARD) for learning interpolative decomposition (ID), which is commonly used for low-rank approximation, feature selection, and identifying hidden patterns in data, where the matrix factors are latent variables associated with each data dimension.

Bayesian Inference feature selection

Autoencoding Conditional GAN for Portfolio Allocation Diversification

no code implementations17 Jun 2022 Jun Lu, Shao Yi

Over the decades, the Markowitz framework has been used extensively in portfolio analysis though it puts too much emphasis on the analysis of the market uncertainty rather than on the trend prediction.

Generative Adversarial Network Time Series +1

Bayesian Low-Rank Interpolative Decomposition for Complex Datasets

no code implementations30 May 2022 Jun Lu

In this paper, we introduce a probabilistic model for learning interpolative decomposition (ID), which is commonly used for feature selection, low-rank approximation, and identifying hidden patterns in data, where the matrix factors are latent variables associated with each data dimension.

Bayesian Inference feature selection

Flexible and Hierarchical Prior for Bayesian Nonnegative Matrix Factorization

no code implementations23 May 2022 Jun Lu, Xuanyu Ye

In this paper, we introduce a probabilistic model for learning nonnegative matrix factorization (NMF) that is commonly used for predicting missing values and finding hidden patterns in the data, in which the matrix factors are latent variables associated with each data dimension.

Bayesian Inference

Gradient Descent, Stochastic Optimization, and Other Tales

no code implementations2 May 2022 Jun Lu

In deep neural networks, the gradient followed by a single sample or a batch of samples is employed to save computational resources and escape from saddle points.

Stochastic Optimization

AdaSmooth: An Adaptive Learning Rate Method based on Effective Ratio

no code implementations2 Apr 2022 Jun Lu

It is well known that we need to choose the hyper-parameters in Momentum, AdaGrad, AdaDelta, and other alternative stochastic optimizers.

Stochastic Optimization

Reducing overestimating and underestimating volatility via the augmented blending-ARCH model

no code implementations15 Mar 2022 Jun Lu, Shao Yi

SVR-GARCH model tends to "backward eavesdrop" when forecasting the financial time series volatility in which case it tends to simply produce the prediction by deviating the previous volatility.

Time Series Time Series Analysis

Exploring Classic Quantitative Strategies

no code implementations23 Feb 2022 Jun Lu

It aims to build a solid foundation on how and why the techniques work.

Matrix Decomposition and Applications

no code implementations1 Jan 2022 Jun Lu

In 1954, Alston S. Householder published Principles of Numerical Analysis, one of the first modern treatments on matrix decomposition that favored a (block) LU decomposition-the factorization of a matrix into the product of lower and upper triangular matrices.

Dual camera snapshot hyperspectral imaging system via physics informed learning

no code implementations6 Sep 2021 Hui Xie, Zhuang Zhao, Jing Han, Yi Zhang, Lianfa Bai, Jun Lu

Various methods using CNNs have been developed in recent years to reconstruct HSIs, but most of the supervised deep learning methods aimed to fit a brute-force mapping relationship between the captured compressed image and standard HSIs.

A survey on Bayesian inference for Gaussian mixture model

no code implementations20 Aug 2021 Jun Lu

The sole aim of this survey is to give a self-contained introduction to concepts and mathematical tools in Bayesian inference for finite and infinite Gaussian mixture model in order to seamlessly introduce their applications in subsequent sections.

Bayesian Inference Clustering +1

Revisit the Fundamental Theorem of Linear Algebra

no code implementations10 Aug 2021 Jun Lu

This survey is meant to provide an introduction to the fundamental theorem of linear algebra and the theories behind them.

Electrical Engineering

Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference

no code implementations22 Jul 2021 Xiaofeng Liu, Bo Hu, Linghao Jin, Xu Han, Fangxu Xing, Jinsong Ouyang, Jun Lu, Georges El Fakhri, Jonghye Woo

In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training.

Bayesian Inference Domain Generalization

A rigorous introduction to linear models

no code implementations10 May 2021 Jun Lu

We then describe linear models from different perspectives and find the properties and theories behind the models.

regression

Imaging vibrations of locally gated, electromechanical few layer graphene resonators with a moving vacuum enclosure

no code implementations4 Jan 2021 Heng Lu, Chen Yang, Ye Tian, Jun Lu, Fanqi Xu, FengNan Chen, Yan Ying, Kevin G. Schädler, Chinhua Wang, Frank H. L. Koppens, Antoine Reserbat-Plantey, Joel Moser

With it we characterize the lowest frequency mode of a FLG resonator by measuring its frequency response as a function of position on the membrane.

Mesoscale and Nanoscale Physics

Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

no code implementations1 Jan 2021 Xiaofeng Liu, Xiongchang Liu, Bo Hu, Wenxuan Ji, Fangxu Xing, Jun Lu, Jane You, C. -C. Jay Kuo, Georges El Fakhri, Jonghye Woo

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids.

Medical Diagnosis Unsupervised Domain Adaptation

Energy-constrained Self-training for Unsupervised Domain Adaptation

no code implementations1 Jan 2021 Xiaofeng Liu, Bo Hu, Xiongchang Liu, Jun Lu, Jane You, Lingsheng Kong

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain.

Image Classification Semantic Segmentation +1

Identity-aware Facial Expression Recognition in Compressed Video

no code implementations1 Jan 2021 Xiaofeng Liu, Linghao Jin, Xu Han, Jun Lu, Jane You, Lingsheng Kong

In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network.

Face Recognition Facial Expression Recognition +1

Alibaba Submission to the WMT18 Parallel Corpus Filtering Task

no code implementations WS 2018 Jun Lu, Xiaoyu Lv, Yangbin Shi, Boxing Chen

This paper describes the Alibaba Machine Translation Group submissions to the WMT 2018 Shared Task on Parallel Corpus Filtering.

Machine Translation Sentence +2

CompNet: Neural networks growing via the compact network morphism

no code implementations27 Apr 2018 Jun Lu, Wei Ma, Boi Faltings

We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact.

MORPH

Reducing over-clustering via the powered Chinese restaurant process

no code implementations15 Feb 2018 Jun Lu, Meng Li, David Dunson

Dirichlet process mixture (DPM) models tend to produce many small clusters regardless of whether they are needed to accurately characterize the data - this is particularly true for large data sets.

Clustering

An Equivalence of Fully Connected Layer and Convolutional Layer

1 code implementation4 Dec 2017 Wei Ma, Jun Lu

The article is helpful for the beginners of the neural network to understand how fully connected layer and the convolutional layer work in the backend.

Hyperprior on symmetric Dirichlet distribution

no code implementations28 Aug 2017 Jun Lu

In this article we introduce how to put vague hyperprior on Dirichlet distribution, and we update the parameter of it by adaptive rejection sampling (ARS).

Machine learning modeling for time series problem: Predicting flight ticket prices

1 code implementation19 May 2017 Jun Lu

Based on the data over a 103 day period, we trained our models, getting the best model - which is AdaBoost-Decision Tree Classification.

BIG-bench Machine Learning General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.